mlsanityData to 14 Oct 2026

GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory Prediction

arXiv 2506.21121 ↗First posted 26 Jun 2025cs.CV cs.ROcited by 7

On the map: Offline RL and imitation learning from data → Imitation and offline RL for driving

also in 1 more
Abstract (arXiv)

Trajectory prediction for surrounding agents is a challenging task in autonomous driving due to its inherent uncertainty and underlying multimodality. Unlike prevailing data-driven methods that primarily rely on supervised learning, in this paper, we introduce a novel Graph-oriented Inverse Reinforcement Learning (GoIRL) framework, which is an IRL-based predictor equipped with vectorized context representations. We develop a feature adaptor to effectively aggregate lane-graph features into grid space, enabling seamless integration with the maximum entropy IRL paradigm to infer the reward distribution and obtain the policy that can be sampled to induce multiple plausible plans. Furthermore, conditioned on the sampled plans, we implement a hierarchical parameterized trajectory generator with a refinement module to enhance prediction accuracy and a probability fusion strategy to boost prediction confidence. Extensive experimental results showcase our approach not only achieves state-of-the-art performance on the large-scale Argoverse & nuScenes motion forecasting benchmarks but also exhibits superior generalization abilities compared to existing supervised models.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Imitation and offline RL for driving, one of 13 directions in Offline RL and imitation learning from data. Builds on 43 of its 55 references that are in the map. First posted on arXiv 26 Jun 2025.

Builds on

43 of 55 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Conditional Predictive Behavior Planning with Inverse Reinforcement Learning for Human-like Autonomous Driving17 Dec
  2. 2018Integrating kinematics and environment context into deep inverse reinforcement learning for predicting off-road vehicle trajectories16 Oct

Other references · 41

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  6. 2016Generative Adversarial Imitation Learningcited by 1,597
  7. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  8. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 690
  9. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 530
  10. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 490
  11. 2018An Algorithmic Perspective on Imitation Learningcited by 459
  12. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 406
29 more
  1. 2020Learning Lane Graph Representations for Motion Forecastingcited by 382
  2. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 295
  3. 2018Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networkscited by 289
  4. 2022Wayformer: Motion Forecasting via Simple & Efficient Attention Networkscited by 280
  5. 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 270
  6. 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
  7. 2021End-to-end Interpretable Neural Motion Plannercited by 242
  8. 2016A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Modelscited by 168
  9. 2021GOHOME: Graph-Oriented Heatmap Output for future Motion Estimationcited by 146
  10. 2021Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Predictioncited by 131
  11. 2021HOME: Heatmap Output for future Motion Estimationcited by 122
  12. 2021LaneRCNN: Distributed Representations for Graph-Centric Motion Forecastingcited by 113
  13. 2021Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversalscited by 113
  14. 2021THOMAS: Trajectory Heatmap Output with learned Multi-Agent Samplingcited by 101
  15. 2021TPCN: Temporal Point Cloud Networks for Motion Forecastingcited by 94
  16. 2020Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Planscited by 72
  17. 2021Learning to Predict Vehicle Trajectories with Model-based Planningcited by 63
  18. 2019Meta-Inverse Reinforcement Learning with Probabilistic Context Variablescited by 50
  19. 2022GANet: Goal Area Network for Motion Forecastingcited by 49
  20. 2020Multimodal Deep Generative Models for Trajectory Prediction: A Conditional Variational Autoencoder Approachcited by 47
  21. 2023MacFormer: Map-Agent Coupled Transformer for Real-time and Robust Trajectory Predictioncited by 32
  22. 2023Dynamic Scenario Representation Learning for Motion Forecasting with Heterogeneous Graph Convolutional Recurrent Networkscited by 28
  23. 2023SEPT: Towards Efficient Scene Representation Learning for Motion Predictioncited by 27
  24. 2024SIMPL: A Simple and Efficient Multi-agent Motion Prediction Baseline for Autonomous Drivingcited by 27
  25. 2019Scene Compliant Trajectory Forecast with Agent-Centric Spatio-Temporal Gridscited by 24
  26. 2022End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Mapscited by 22
  27. 2021Trajectory Prediction with Graph-based Dual-scale Context Fusioncited by 19
  28. 2024Improving Out-of-Distribution Generalization of Trajectory Prediction for Autonomous Driving via Polynomial Representationscited by 9
  29. 2023PBP: Path-based Trajectory Prediction for Autonomous Drivingcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 2.

7 papers.

  1. 2025Advancing Multi-agent Traffic Simulation via R1-Style Reinforcement Fine-Tuningcited by 14
  2. 2025ColaVLA: Leveraging Cognitive Latent Reasoning for Hierarchical Parallel Trajectory Planning in Autonomous Drivingcited by 11
  3. 2025Foresight in Motion: Reinforcing Trajectory Prediction with Reward Heuristicscited by 6
  4. 2026VG3S: Visual Geometry Grounded Gaussian Splatting for Semantic Occupancy Predictioncited by 5
  5. 2025ST-GS: Vision-Based 3D Semantic Occupancy Prediction with Spatial-Temporal Gaussian Splattingcited by 4
  6. 2026Adapter-Augmented Bandits for Online Multi-Constrained Multi-Modal Inference Schedulingcited by 2
  7. 2025ILNet: Trajectory Prediction with Inverse Learning Attention for Enhancing Intention Capturecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Driving in Real Life with Inverse Reinforcement Learning
  2. 2025Generalizable Trajectory Prediction via Inverse Reinforcement Learning with Mamba-Graph Architecture
  3. 2020Efficient Sampling-Based Maximum Entropy Inverse Reinforcement Learning with Application to Autonomous Driving
  4. 2026Game-Theoretic Inverse Reinforcement Learning for Modeling Competitive Human Driving: A Cut-in Prediction Study
  5. 2018Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning
  6. 2025TreeIRL: Safe Urban Driving with Tree Search and Inverse Reinforcement Learning
  7. 2020Planning on the fast lane: Learning to interact using attention mechanisms in path integral inverse reinforcement learning
  8. 2023NashFormer: Leveraging Local Nash Equilibria for Semantically Diverse Trajectory Prediction